Answers are grounded in this paper and cite their sources.
Cross-correlation between a trigger-averaged event-related potential (ERP) template and continuous electrocorticogram was used to detect movement-related ERP's. The accuracy of ERP detection for the five best subjects (of 17 studied), had hit percentages >90% and false positive percentages <10%. These cases were considered appropriate for operation of a direct brain interface.
No takes yet. Share an insight, caveat, or question.
Levine et al. (2000) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: